Liquid AI, a startup founded by former MIT researchers, has unveiled LEAP, the Liquid Edge AI Platform, and Apollo to bring edge AI to developers. LEAP is a cross-platform SDK that allows developers to integrate small language models directly into mobile applications, addressing the need for privacy-preserving, efficient AI on consumer hardware.
LEAP is designed for mobile developers with no prior ML experience, making it easy to add to iOS or Android projects with just a few lines of code. The SDK offers a local-first approach, allowing small models to run directly on devices, reducing reliance on cloud infrastructure. LEAP is OS- and model-agnostic, supporting both iOS and Android platforms.
The goal of LEAP is to create a unified ecosystem for edge AI, offering developers tools to discover, adapt, test, and deploy SLMs for edge use. Developers can browse a curated model catalog with various quantization and checkpoint options to tailor performance and memory footprint to target devices. Apollo, a companion iOS app, allows developers to interact with LEAP-compatible models offline, preserving user privacy and reducing reliance on cloud compute.
Overall, the LEAP SDK release builds on Liquid AI’s foundation model family, LFM2, optimized for on-device workloads. The SDK is currently free to use under a developer license, with premium enterprise features available under a separate commercial license in the future. Developers can access the LEAP SDK website, download Apollo from the App Store, or join the Liquid AI developer community on Discord to get started.
